Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    latex math output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contracted
    0.40
     fours
    0.39
    SHORT
    0.39
     monumento
    0.38
    поряд
    0.38
     PERSONNEL
    0.38
     shortened
    0.38
     eyesight
    0.38
     thoroughly
    0.38
     dodgy
    0.38
    POSITIVE LOGITS
     output
    0.54
     salida
    0.50
     Output
    0.49
    出力
    0.49
    Output
    0.48
     输出
    0.47
    output
    0.47
    |+
    0.47
     вышел
    0.47
    ida
    0.46
    Act Density 0.000%

    No Known Activations